Infrastructure as a Service

Cloud Infrastructure as a Service

Join us to learn more from a community of collaborative experts and IBM Cloud product users to share advice and best practices with peers and stay up to date regarding product enhancements, regional user group meetings, webinars, how-to blogs, and other helpful materials.

 View Only
Back to discussions
Expand all | Collapse all

Unlock Scalable AI Tooling with MCP Servers on IBM Cloud Code Engine + IBM Cloud Object Storage

  • 1.  Unlock Scalable AI Tooling with MCP Servers on IBM Cloud Code Engine + IBM Cloud Object Storage

    Posted 6 hours ago

    Looking to extend your LLMs with real-world capabilities like web fetching and file access? Start with Jeremias Werner's blog-a hands-on guide to deploying Model Context Protocol (MCP) servers on IBM Cloud Code Engine, backed by IBM Cloud Object Storage (COS).

    What You'll Learn:

    • How to deploy MCP servers (mcp-npx-fetch, server-filesystem) as containers on Code Engine.
    • How to expose them via SSE using supergateway for remote LLM access.
    • How to integrate with COS for persistent, scalable, and secure file storage.

    Why It Matters:

    • Code Engine provides serverless, auto-scaling infrastructure-perfect for MCP tools that idle until called.
    • COS enables LLMs to read/write files across sessions, share context between agents, and store outputs securely.
    • Supergateway bridges local MCP tools to HTTP endpoints, making them usable by clients like Claude Desktop and LangChain.

    Use Cases:

    • Summarize live web pages with fetch_txt.
    • Read/write shared documents with read_txt and write_txt.
    • Build enterprise-grade tools that wrap internal services like IBM MQ or Process Mining.

    🔗 Ready to build smarter agents with scalable infrastructure?
    Read the full blog here



    ------------------------------
    Danielle Kingberg
    Sr. GTM Product Manager, IBM Cloud Object Storage
    ------------------------------


Related Content